plugins/spec-kitty-plugin/skills/spec-kitty-sync-plugin/SKILL.md
Full-cycle install or update of the Spec-Kitty framework - upgrades the CLI, refreshes templates, syncs the plugin, reconciles custom knowledge, and bridges to agent environments. Custom skill (not from upstream spec-kitty).
npx skillsauth add richfrem/agent-plugins-skills spec-kitty-sync-pluginInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill requires Python 3.8+ and standard library only. No external dependencies.
[!TIP] See INSTALL.md for instructions on how to install missing dependencies.
To install this skill's dependencies:
pip-compile ./requirements.in
pip install -r ./requirements.txt
See ./requirements.txt for the dependency lockfile (currently empty — standard library only).
You are an active administrator for the Spec-Driven Development framework. This skill handles both initial setup and ongoing updates, ensuring the CLI, templates, plugin, and agent environments are all in sync.
Key principle: This project maintains two layers of knowledge:
The sync must NEVER overwrite custom augmented knowledge. Instead, the agent reviews upstream changes and intelligently reconciles them with existing custom content.
references/diagrams/sync-plugin-flow.mmdreferences/diagrams/init-install-flow.mmdCRITICAL RULE: Do not simulate these steps. You must invoke the bash commands and read their outputs.
Check if .kittify/ exists in the project root:
test -d .kittify && echo "UPDATE" || echo "INIT"
spec-kitty init . (no --force).spec-kitty init . --force.Install or update the spec-kitty-cli package:
pip install --upgrade spec-kitty-cli
Confirm the installed version:
spec-kitty --version
Pull the latest command templates, mission configs, and scripts into .kittify/:
INIT mode (first time):
spec-kitty init . --ai windsurf
This creates .kittify/, .windsurf/workflows/, mission configs, and git hooks.
UPDATE mode (existing project):
spec-kitty init . --ai windsurf --force
This refreshes existing templates without affecting project-specific configs.
Convert the refreshed .kittify/ templates into distributable plugin components inside the spec-kitty-plugin directory:
python ./scripts/sync_configuration.py
This generates skills, rules, and templates that agents can consume.
IMPORTANT: This step ONLY touches auto-generated files (14 command skill SKILL.md files, rules, templates). It does NOT touch custom skills listed below.
This is the intelligence step. After the automated sync, you MUST review what changed and reconcile with custom augmented skills.
Compare the new .kittify/ content against what was there before:
git diff --stat -- .kittify/ .windsurf/ ../../
Summarize the key changes for the user (new commands, removed commands, changed templates, updated mission configs).
The following contain custom augmented knowledge that is NOT generated by sync_configuration.py. They MUST be reviewed for staleness after every upstream update:
Custom Skills (in skills/, never touched by sync):
| Custom Skill | Contains | Review For |
|---|---|---|
| skills/spec-kitty-workflow/SKILL.md | End-to-end workflow guide, safety steps, best practices | New commands/phases added upstream, safety guidance still accurate |
| skills/spec-kitty-sync-plugin/SKILL.md | This skill (meta) | Script paths still valid, new sync features |
| skills/spec-kitty-agent/SKILL.md | Agent config sync, combined lifecycle | New agent configs, changes to sync scripts |
AUGMENTED.md Files (in skills/*/references/, adjacent to auto-synced SKILL.md — never overwritten):
| Augmented File | Contains | Review For |
|---|---|---|
| references/AUGMENTED.md | Pre-merge safety protocol, branch protection awareness, kitty-specs conflict resolution | New merge flags, changed CLI behavior |
| references/AUGMENTED.md | Worktree discipline, commit hygiene, dependency management | New implement flags, changed validation rules |
| references/AUGMENTED.md | Batch review protocol, review standards, dependency verification | New review commands, changed lane logic |
For each custom skill:
.kittify/ command templatesIf changes are needed in custom skills:
Present proposed changes to the user in diff format before applying them.
Before completing the sync, verify these files were NOT deleted or corrupted:
./rules/constitution.md./references/standard-workflow-rules.mdtest -f ./rules/constitution.md && echo "constitution OK" || echo "MISSING!"
Escalation Taxonomy (Missing Data Response)
If ANY protected file is missing or ls returns an error, trigger the Escalation Taxonomy:
🚨 PROTECTED FILE MISSING 🚨git checkout -- <file>.ASK THE USER before deploying:
Which plugins should I install/update?
- Only spec-kitty-plugin (just the updated spec-kitty commands)
- All plugins (full ecosystem sync across all 80+ plugins)
After performing the sync, you must deploy the updated plugin to your agent environment.
[!IMPORTANT] Zero Inline Commands: See the central installation guide for the authoritative deployment logic:
👉 INSTALL.md
This handles both forced re-installation and full ecosystem synchronization across all 80+ plugins.
Inform the user:
tools
Ingests repository files into the ChromaDB vector store. Builds or updates the vector index from a manifest or directory scan using ingest.py. Use when new files need to be indexed or the vector store is out of date. <example> user: "Index these new plugin files into the vector database" assistant: "I'll use vector-db-ingest to add them to the vector store." </example> <example> user: "The vector store is missing recent files -- update it" assistant: "I'll use vector-db-ingest to re-index the changes." </example>
data-ai
Removes stale and orphaned chunks from the ChromaDB vector store for files that have been deleted or renamed. Use after files are removed or moved to keep the vector index in sync with the filesystem. <example> user: "Clean up the vector store after I deleted some files" assistant: "I'll use vector-db-cleanup to remove orphaned chunks." </example> <example> user: "The vector database has chunks for files that no longer exist" assistant: "I'll run vector-db-cleanup to prune them." </example>
testing
Audit Vector DB coverage -- compares the live filesystem manifest against the ChromaDB index to identify coverage gaps.
development
3-Phase Knowledge Search strategy for the RLM Factory ecosystem. Auto-invoked when tasks involve finding code, documentation, or architecture context in the repository. Enforces the optimal search order: RLM Summary Scan (O(1)) -> Vector DB Semantic Search -> Grep/Exact Match. Never skip phases.